Summary: The Gini Index is calculated by subtracting the sum of the squared probabilities of each class from one. It favors larger partitions. Information Gain multiplies the probability of the class times the log (base=2) of that class probability. Information Gain favors smaller partitions with many distinct values. Ultimately, you have to experiment with your data […]
Summary: Taking a big problem, question, or analysis and breaking it into chunks frees you from the burden of trying to keep all the plates spinning at once. Compartmentalizing and identifying the dependencies at each step helps you reason out what needs to be done and looked into further. One of the first problems […]
Summary: Every great analyst knows the core numbers like the back of their hand. Build yourself a cheat sheet (whether it’s a list of stats or an interactive dashboard) and keep it up-to-date. The more you can internalize the numbers, the smarter you’ll look (and be). The #1 thing that differentiates a great analyst […]
As I work on my python script to parse SAS Enterprise Guide projects, I’ve been using git and github to keep track of my changes and keep a stable project while I break things and try to make it better. However, as per my previous post on github, It can be frustrating to work with […]
GitHub is extremely frustrating at times. Especially when you spend more time tweaking your settings rather than writing / committing code. I’m going to walk through a couple situations that I’ve ran into. If you’re looking for a broader, simple tutorial, the git – the simple guide fits that bill nicely as well. Connect an Existing Directory […]